© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130031
    Prev
    Next
    INDEX
    Explanations

    accounting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç§ijæĬĢèĤ¡ä»½
    -0.30
    atab
    -0.27
    emons
    -0.26
    odem
    -0.25
    aten
    -0.25
    elong
    -0.25
     crackers
    -0.24
    èİĵ
    -0.24
    arming
    -0.24
    çłĶ究表æĺİ
    -0.24
    POSITIVE LOGITS
    ulle
    0.27
    ours
    0.27
    æ·±å±Ĥ次
    0.27
    pires
    0.26
    infer
    0.26
    æĽ´æ·±
    0.26
    æ·±å±Ĥ
    0.25
    大åºĨ
    0.25
    åĿ¼
    0.24
    alk
    0.23
    Activations Density 3.323%

    No Known Activations